skills/joeplouis/video-production-skills-openmontage/vercel-react-best-practices/Gen Agent Trust Hub
vercel-react-best-practices
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor user-provided React and Next.js source code, which creates an ingestion point for untrusted data. This makes the agent potentially susceptible to malicious instructions embedded within the code it processes (e.g., inside comments or string literals).\n
- Ingestion points: User-provided source code snippets and files processed during React/Next.js development, refactoring, or code review tasks.\n
- Boundary markers: The skill does not provide the agent with specific delimiters or explicit instructions to ignore commands that may be embedded in the user's source code.\n
- Capability inventory: The agent has the capability to generate code, modify existing project files, and perform performance audits based on these rules.\n
- Sanitization: The skill lacks defined mechanisms for sanitizing or filtering user-provided code content before it is analyzed by the agent.
Audit Metadata